E-CodeTI-84 Plus CE statistics programs
9 checked statistics programs for the TI-84 Plus CE. Each one runs in E-Code's virtual calculator in your browser, and you can put it on your own calculator.
The programs
- Regression: linear, quadratic, exponential with r²: Type X and Y lists: 2-variable statistics and correlation, then the linear, quadratic and exponential fits with r² (the exponential one also in Y terms, so the three are comparable).
- Hypothesis tests: z, t, two-sample t, chi-square: One-sample z and t tests, the two-sample (Welch) t test and the chi-square goodness-of-fit test from summary numbers: test statistic, degrees of freedom, p-value for the chosen tail, and the reject / do-not-reject decision at your alpha.
- Confidence intervals: z, t, proportion, two-sample: Confidence interval for a mean (sigma known or not), a proportion, or a difference of two means (Welch): lower and upper limits, center, margin of error, critical value and degrees of freedom.
- Binomial, Poisson and normal probabilities: Binomial and Poisson P(X=a), P(X≤b), P(a≤X≤b), P(X≥a) with mean and SD; normal P(a<X<b), tails and z-scores; inverse normal for a left area, plus the central interval.
- One-way ANOVA: Compare the means of 2 to 6 groups: type each group's data, get the between- and within-group sums of squares, degrees of freedom, the F statistic, its p-value and eta squared.
- Chi-square test of independence: Type a contingency table row by row: the chi-square statistic from the expected counts, degrees of freedom, p-value and Cramér's V, with a warning when any expected count is under 5.
- Sample size for a margin of error: How many observations you need for a chosen confidence level and margin of error: estimating one mean (known sigma), one proportion (p-hat or the safe .5), or the difference of two means (per group), rounded up.
- Geometric distribution: first success: Chance the first success comes on trial k, by trial k, or after trial k, with the mean and standard deviation of the waiting time.
- Normal approximation to the binomial: P(a ≤ X ≤ b) for a binomial, exactly and by the normal approximation with and without the continuity correction, the errors of each, and whether np and n(1-p) are both at least 10.